SDF-TAR: Parallel Tracking and Refinement in RGB-D Data using Volumetric Registration

@inproceedings{Slavcheva2016SDFTARPT,
  title={SDF-TAR: Parallel Tracking and Refinement in RGB-D Data using Volumetric Registration},
  author={Miroslava Slavcheva and Slobodan Ilic},
  booktitle={BMVC},
  year={2016}
}
This paper introduces SDF-TAR: a real-time SLAM system based on volumetric registration in RGB-D data. While the camera is tracked online on the GPU, the most recently estimated poses are jointly refined on the CPU. We perform registration by aligning the data in limited-extent volumes anchored at salient 3D locations. This strategy permits efficient tracking on the GPU. Furthermore, the small memory load of the partial volumes allows for pose refinement to be done concurrently on the CPU. This… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 55 references

SDF Tracker: A parallel algorithm for on-line pose estimation and scene reconstruction from depth images

2013 IEEE/RSJ International Conference on Intelligent Robots and Systems • 2013
View 9 Excerpts
Highly Influenced

A benchmark for the evaluation of RGB-D SLAM systems

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems • 2012
View 6 Excerpts
Highly Influenced

An evaluation of the RGB-D SLAM system

2012 IEEE International Conference on Robotics and Automation • 2012
View 13 Excerpts
Highly Influenced

Registration without ICP

Computer Vision and Image Understanding • 2004
View 5 Excerpts
Highly Influenced

A Method for Registration of 3-D Shapes

IEEE Trans. Pattern Anal. Mach. Intell. • 1992
View 5 Excerpts
Highly Influenced

CoRBS: Comprehensive RGB-D benchmark for SLAM using Kinect v2

2016 IEEE Winter Conference on Applications of Computer Vision (WACV) • 2016
View 3 Excerpts

Similar Papers

Loading similar papers…